Premium
Correlated Residuals in Non‐Linear Regression Applied to Growth Data
Author(s) -
Glasbey C. A.
Publication year - 1979
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2347195
Subject(s) - statistics , linear regression , regression analysis , mathematics , regression , econometrics
S ummary A model for growth is proposed which has as the stochastic term a first‐order autoregressive process. This remedies a deficiency in the literature for non‐linear regression with correlated residuals (Sprent, 1969, p. 158). In Section 2 a method of fitting this model is given and in Section 3 this is applied to animal weight data using the generalized logistic curve. The assumptions of the model are examined in Section 4 and in Section 5 the data are further analysed. Finally, generalizations of the model are outlined in Section 6.